# importing libraries

​

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

import missingno as msno

​

import warnings

warnings.filterwarnings('ignore')

​

from sklearn.model_selection import train_test_split, GridSearchCV

from sklearn.preprocessing import StandardScaler

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

from sklearn.linear_model import LogisticRegression

from sklearn.neighbors import KNeighborsClassifier

from sklearn.svm import SVC

from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier

from sklearn.ensemble import RandomForestClassifier

from sklearn.ensemble import AdaBoostClassifier

from sklearn.ensemble import GradientBoostingClassifier

from xgboost import XGBClassifier

from catboost import CatBoostClassifier

from sklearn.ensemble import ExtraTreesClassifier

from lightgbm import LGBMClassifier

from sklearn.ensemble import VotingClassifier

​

import folium

from folium.plugins import HeatMap

import plotly.express as px

​

plt.style.use('fivethirtyeight')

%matplotlib inline

pd.set_option('display.max_columns', 32)

# reading data

​

df = pd.read_csv("C:/Users/VANAM GANESH/Downloads/hotel_bookings.csv/hotel_bookings.csv")

df.head()

df.describe()

df.info()

# checking for null values 

​

null = pd.DataFrame({'Null Values' : df.isna().sum(), 'Percentage Null Values' : (df.isna().sum()) / (df.shape[0]) * (100)})

null

# filling null values with zero

​

df.fillna(0, inplace = True)

# visualizing null values

​

msno.bar(df)

plt.show()

# adults, babies and children cant be zero at same time, so dropping the rows having all these zero at same time

​

filter = (df.children == 0) & (df.adults == 0) & (df.babies == 0)

df[filter]

df = df[~filter]

df

country_wise_guests = df[df['is_canceled'] == 0]['country'].value_counts().reset_index()

country_wise_guests.columns = ['country', 'No of guests']

country_wise_guests

basemap = folium.Map()

guests_map = px.choropleth(country_wise_guests, locations = country_wise_guests['country'],

                           color = country_wise_guests['No of guests'], hover_name = country_wise_guests['country'])

guests_map.show()

df.head()

data = df[df['is_canceled'] == 0]

​

px.box(data_frame = data, x = 'reserved_room_type', y = 'adr', color = 'hotel', template = 'plotly_dark')

data_resort = df[(df['hotel'] == 'Resort Hotel') & (df['is_canceled'] == 0)]

data_city = df[(df['hotel'] == 'City Hotel') & (df['is_canceled'] == 0)]

resort_hotel = data_resort.groupby(['arrival_date_month'])['adr'].mean().reset_index()

resort_hotel

city_hotel=data_city.groupby(['arrival_date_month'])['adr'].mean().reset_index()

city_hotel

final_hotel = resort_hotel.merge(city_hotel, on = 'arrival_date_month')

final_hotel.columns = ['month', 'price_for_resort', 'price_for_city_hotel']

final_hotel

!pip install sort-dataframeby-monthorweek

​

!pip install sorted-months-weekdays

import sort_dataframeby_monthorweek as sd

​

def sort_month(df, column_name):

    return sd.Sort_Dataframeby_Month(df, column_name)

final_prices = sort_month(final_hotel, 'month')

final_prices

plt.figure(figsize = (17, 8))

​

px.line(final_prices, x = 'month', y = ['price_for_resort','price_for_city_hotel'],

        title = 'Room price per night over the Months', template = 'plotly_dark')

resort_guests = data_resort['arrival_date_month'].value_counts().reset_index()

resort_guests.columns=['month','no of guests']

resort_guests

city_guests = data_city['arrival_date_month'].value_counts().reset_index()

city_guests.columns=['month','no of guests']

city_guests

final_guests = resort_guests.merge(city_guests,on='month')

final_guests.columns=['month','no of guests in resort','no of guest in city hotel']

final_guests